{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T02:08:54Z","timestamp":1768010934571,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T00:00:00Z","timestamp":1571011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,14]]},"DOI":"10.1145\/3340555.3353742","type":"proceedings-article","created":{"date-parts":[[2019,10,17]],"date-time":"2019-10-17T12:49:48Z","timestamp":1571316588000},"page":"6-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":41,"title":["Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approach"],"prefix":"10.1145","author":[{"given":"Ognjen","family":"Rudovic","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, USA"}]},{"given":"Meiru","family":"Zhang","sequence":"additional","affiliation":[{"name":"Imperial College London, United Kingdom"}]},{"given":"Bjorn","family":"Schuller","sequence":"additional","affiliation":[{"name":"GLAM - Group on Language, Audio & Music, United Kingdom"}]},{"given":"Rosalind","family":"Picard","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, USA"}]}],"member":"320","published-online":{"date-parts":[[2019,10,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2015. Empatica E4: https:\/\/www.empatica.com\/en-eu\/research\/e4\/.  2015. Empatica E4: https:\/\/www.empatica.com\/en-eu\/research\/e4\/."},{"key":"e_1_3_2_1_2_1","volume-title":"Multimodal Behavior Analysis in the Wild","author":"Alameda-Pineda Xavier","unstructured":"Xavier Alameda-Pineda , Elisa Ricci , and Nicu Sebe . 2019. Multimodal behavior analysis in the wild: An introduction . In Multimodal Behavior Analysis in the Wild . Elsevier , 1\u20138. Xavier Alameda-Pineda, Elisa Ricci, and Nicu Sebe. 2019. Multimodal behavior analysis in the wild: An introduction. In Multimodal Behavior Analysis in the Wild. Elsevier, 1\u20138."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25446-8_4"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2663241"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1647314.1647336"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264986"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"e_1_3_2_1_11_1","unstructured":"Yan Duan John Schulman Xi Chen Peter\u00a0L Bartlett Ilya Sutskever and Pieter Abbeel. 2016. RL2: Fast Reinforcement Learning via Slow Reinforcement Learning. arXiv preprint arXiv:1611.02779(2016).  Yan Duan John Schulman Xi Chen Peter\u00a0L Bartlett Ilya Sutskever and Pieter Abbeel. 2016. RL2: Fast Reinforcement Learning via Slow Reinforcement Learning. arXiv preprint arXiv:1611.02779(2016)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1196\/annals.1382.016"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Meng Fang Yuan Li and Trevor Cohn. 2017. Learning how to active learn: A deep reinforcement learning approach. arXiv preprint arXiv:1708.02383(2017).  Meng Fang Yuan Li and Trevor Cohn. 2017. Learning how to active learn: A deep reinforcement learning approach. arXiv preprint arXiv:1708.02383(2017).","DOI":"10.18653\/v1\/D17-1063"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Michael\u00a0A Goodrich Alan\u00a0C Schultz 2008. Human\u2013robot interaction: a survey. Foundations and Trends\u00ae in Human\u2013Computer Interaction 1 3(2008) 203\u2013275.  Michael\u00a0A Goodrich Alan\u00a0C Schultz 2008. Human\u2013robot interaction: a survey. Foundations and Trends\u00ae in Human\u2013Computer Interaction 1 3(2008) 203\u2013275.","DOI":"10.1561\/1100000005"},{"key":"e_1_3_2_1_17_1","volume-title":"Second Language Skills. In Thirtieth AAAI Conference on Artificial Intelligence. http:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI16\/paper\/view\/11759","author":"Gordon Goren","year":"2016","unstructured":"Goren Gordon , Samuel Spaulding , Jacqueline\u00a0Kory Westlund , Jin\u00a0Joo Lee , Luke Plummer , Marayna Martinez , Madhurima Das , and Cynthia Breazeal . 2016 . Affective Personalization of a Social Robot Tutor for Children\u2019s Second Language Skills. In Thirtieth AAAI Conference on Artificial Intelligence. http:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI16\/paper\/view\/11759 Goren Gordon, Samuel Spaulding, Jacqueline\u00a0Kory Westlund, Jin\u00a0Joo Lee, Luke Plummer, Marayna Martinez, Madhurima Das, and Cynthia Breazeal. 2016. Affective Personalization of a Social Robot Tutor for Children\u2019s Second Language Skills. In Thirtieth AAAI Conference on Artificial Intelligence. http:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI16\/paper\/view\/11759"},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Machine Learning. 1764\u20131772","author":"Graves Alex","year":"2014","unstructured":"Alex Graves and Navdeep Jaitly . 2014 . Towards end-to-end speech recognition with recurrent neural networks . In International Conference on Machine Learning. 1764\u20131772 . Alex Graves and Navdeep Jaitly. 2014. Towards end-to-end speech recognition with recurrent neural networks. In International Conference on Machine Learning. 1764\u20131772."},{"key":"e_1_3_2_1_19_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber . 1997. Long short-term memory. Neural computation 9, 8 ( 1997 ), 1735\u20131780. Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735\u20131780."},{"key":"e_1_3_2_1_20_1","volume-title":"Multimodal human\u2013computer interaction: A survey. Computer vision and image understanding 108, 1-2","author":"Jaimes Alejandro","year":"2007","unstructured":"Alejandro Jaimes and Nicu Sebe . 2007. Multimodal human\u2013computer interaction: A survey. Computer vision and image understanding 108, 1-2 ( 2007 ), 116\u2013134. Alejandro Jaimes and Nicu Sebe. 2007. Multimodal human\u2013computer interaction: A survey. Computer vision and image understanding 108, 1-2 (2007), 116\u2013134."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-017-1755-6"},{"key":"e_1_3_2_1_22_1","unstructured":"Christoph K\u00e4ding Erik Rodner Alexander Freytag and Joachim Denzler. 2016. Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes. arXiv preprint arXiv:1612.06129(2016).  Christoph K\u00e4ding Erik Rodner Alexander Freytag and Joachim Denzler. 2016. Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes. arXiv preprint arXiv:1612.06129(2016)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0195-2"},{"key":"e_1_3_2_1_24_1","unstructured":"Ksenia Konyushkova Raphael Sznitman and Pascal Fua. 2017. Learning active learning from data. In Advances in Neural Information Processing Systems. 4228\u20134238.  Ksenia Konyushkova Raphael Sznitman and Pascal Fua. 2017. Learning active learning from data. In Advances in Neural Information Processing Systems. 4228\u20134238."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-1033"},{"key":"e_1_3_2_1_26_1","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602(2013).  Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602(2013)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622572.1622579"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817122"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301687"},{"key":"e_1_3_2_1_30_1","unstructured":"Xin Qian Ziyi Zhong and Jieli Zhou. 2018. Multimodal machine translation with reinforcement learning. arXiv preprint arXiv:1805.02356(2018).  Xin Qian Ziyi Zhong and Jieli Zhou. 2018. Multimodal machine translation with reinforcement learning. arXiv preprint arXiv:1805.02356(2018)."},{"key":"e_1_3_2_1_31_1","volume-title":"Personalized Machine Learning for Robot Perception of Affect and Engagement in Autism Therapy. Science Robotics","author":"Rudovic Ognjen","year":"2018","unstructured":"Ognjen Rudovic , Jaeryoung Lee , Miles Dai , Bjorn Schuller , and Rosalind Picard . 2018. Personalized Machine Learning for Robot Perception of Affect and Engagement in Autism Therapy. Science Robotics ( 2018 ). Ognjen Rudovic, Jaeryoung Lee, Miles Dai, Bjorn Schuller, and Rosalind Picard. 2018. Personalized Machine Learning for Robot Perception of Affect and Engagement in Autism Therapy. Science Robotics (2018)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2017.00036"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1957656.1957781"},{"key":"e_1_3_2_1_34_1","first-page":"55","article-title":"Active learning literature survey. University of Wisconsin","volume":"52","author":"Settles Burr","year":"2010","unstructured":"Burr Settles . 2010 . Active learning literature survey. University of Wisconsin , Madison 52 , 55 - 66 (2010), 11. Burr Settles. 2010. Active learning literature survey. University of Wisconsin, Madison 52, 55-66 (2010), 11.","journal-title":"Madison"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_1_36_1","unstructured":"Christiana Tsiourti Astrid Weiss Katarzyna Wac and Markus Vincze. 2019. Multimodal Integration of Emotional Signals from Voice Body and Context: Effects of (In) Congruence on Emotion Recognition and Attitudes Towards Robots. International Journal of Social Robotics(2019) 1\u201319.  Christiana Tsiourti Astrid Weiss Katarzyna Wac and Markus Vincze. 2019. Multimodal Integration of Emotional Signals from Voice Body and Context: Effects of (In) Congruence on Emotion Recognition and Attitudes Towards Robots. International Journal of Social Robotics(2019) 1\u201319."},{"key":"e_1_3_2_1_37_1","unstructured":"Jane\u00a0X Wang Zeb Kurth-Nelson Dhruva Tirumala Hubert Soyer Joel\u00a0Z Leibo Remi Munos Charles Blundell Dharshan Kumaran and Matt Botvinick. 2016. Learning to reinforcement learn. arXiv preprint arXiv:1611.05763(2016).  Jane\u00a0X Wang Zeb Kurth-Nelson Dhruva Tirumala Hubert Soyer Joel\u00a0Z Leibo Remi Munos Charles Blundell Dharshan Kumaran and Matt Botvinick. 2016. Learning to reinforcement learn. arXiv preprint arXiv:1611.05763(2016)."},{"key":"e_1_3_2_1_38_1","volume-title":"Cost-effective active learning for deep image classification","author":"Wang Keze","year":"2016","unstructured":"Keze Wang , Dongyu Zhang , Ya Li , Ruimao Zhang , and Liang Lin . 2016. Cost-effective active learning for deep image classification . IEEE Transactions on Circuits and Systems for Video Technology ( 2016 ). Keze Wang, Dongyu Zhang, Ya Li, Ruimao Zhang, and Liang Lin. 2016. Cost-effective active learning for deep image classification. IEEE Transactions on Circuits and Systems for Video Technology (2016)."},{"key":"e_1_3_2_1_39_1","volume-title":"Deep Reinforcement Learning Workshop(2016)","author":"Woodward Mark","year":"2016","unstructured":"Mark Woodward and Chelsea Finn . 2016 . Active one-shot learning. NIPS , Deep Reinforcement Learning Workshop(2016) . Mark Woodward and Chelsea Finn. 2016. Active one-shot learning. NIPS, Deep Reinforcement Learning Workshop(2016)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Jiaping Zhang Tiancheng Zhao and Zhou Yu. 2018. Multimodal hierarchical reinforcement learning policy for task-oriented visual dialog. arXiv preprint arXiv:1805.03257(2018).  Jiaping Zhang Tiancheng Zhao and Zhou Yu. 2018. Multimodal hierarchical reinforcement learning policy for task-oriented visual dialog. arXiv preprint arXiv:1805.03257(2018).","DOI":"10.18653\/v1\/W18-5015"}],"event":{"name":"ICMI '19: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Suzhou China","acronym":"ICMI '19"},"container-title":["2019 International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3340555.3353742","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3340555.3353742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:28Z","timestamp":1750202008000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3340555.3353742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,14]]},"references-count":40,"alternative-id":["10.1145\/3340555.3353742","10.1145\/3340555"],"URL":"https:\/\/doi.org\/10.1145\/3340555.3353742","relation":{},"subject":[],"published":{"date-parts":[[2019,10,14]]},"assertion":[{"value":"2019-10-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}